diff options
Diffstat (limited to 'clang/test/CodeGen/X86/avx512-reduceMinMaxIntrin.c')
| -rw-r--r-- | clang/test/CodeGen/X86/avx512-reduceMinMaxIntrin.c | 116 |
1 files changed, 66 insertions, 50 deletions
diff --git a/clang/test/CodeGen/X86/avx512-reduceMinMaxIntrin.c b/clang/test/CodeGen/X86/avx512-reduceMinMaxIntrin.c index 3e33ec5..309fc28 100644 --- a/clang/test/CodeGen/X86/avx512-reduceMinMaxIntrin.c +++ b/clang/test/CodeGen/X86/avx512-reduceMinMaxIntrin.c @@ -1,164 +1,180 @@ -// RUN: %clang_cc1 -ffreestanding %s -O0 -triple=x86_64-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror | FileCheck %s +// RUN: %clang_cc1 -x c -ffreestanding %s -O0 -triple=x86_64-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror | FileCheck %s +// RUN: %clang_cc1 -x c -ffreestanding %s -O0 -triple=i386-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror | FileCheck %s +// RUN: %clang_cc1 -x c++ -ffreestanding %s -O0 -triple=x86_64-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror | FileCheck %s +// RUN: %clang_cc1 -x c++ -ffreestanding %s -O0 -triple=i386-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror | FileCheck %s + +// RUN: %clang_cc1 -x c -ffreestanding %s -O0 -triple=x86_64-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror -fexperimental-new-constant-interpreter | FileCheck %s +// RUN: %clang_cc1 -x c -ffreestanding %s -O0 -triple=i386-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror -fexperimental-new-constant-interpreter | FileCheck %s +// RUN: %clang_cc1 -x c++ -ffreestanding %s -O0 -triple=x86_64-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror -fexperimental-new-constant-interpreter | FileCheck %s +// RUN: %clang_cc1 -x c++ -ffreestanding %s -O0 -triple=i386-apple-darwin -target-cpu skylake-avx512 -emit-llvm -o - -Wall -Werror -fexperimental-new-constant-interpreter | FileCheck %s #include <immintrin.h> +#include "builtin_test_helpers.h" long long test_mm512_reduce_max_epi64(__m512i __W){ -// CHECK-LABEL: @test_mm512_reduce_max_epi64( -// CHECK: call i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_max_epi64 +// CHECK: call {{.*}}i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> %{{.*}}) return _mm512_reduce_max_epi64(__W); } +TEST_CONSTEXPR(_mm512_reduce_max_epi64((__m512i)(__v8di){-4, -3, -2, -1, 0, 1, 2, 3}) == 3); unsigned long long test_mm512_reduce_max_epu64(__m512i __W){ -// CHECK-LABEL: @test_mm512_reduce_max_epu64( -// CHECK: call i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_max_epu64 +// CHECK: call {{.*}}i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> %{{.*}}) return _mm512_reduce_max_epu64(__W); } +TEST_CONSTEXPR(_mm512_reduce_max_epu64((__m512i)(__v8du){0, 1, 2, 3, 4, 5, 6, 7}) == 7); double test_mm512_reduce_max_pd(__m512d __W, double ExtraAddOp){ -// CHECK-LABEL: @test_mm512_reduce_max_pd( +// CHECK-LABEL: test_mm512_reduce_max_pd // CHECK-NOT: nnan -// CHECK: call nnan double @llvm.vector.reduce.fmax.v8f64(<8 x double> %{{.*}}) +// CHECK: call nnan {{.*}}double @llvm.vector.reduce.fmax.v8f64(<8 x double> %{{.*}}) // CHECK-NOT: nnan return _mm512_reduce_max_pd(__W) + ExtraAddOp; } long long test_mm512_reduce_min_epi64(__m512i __W){ -// CHECK-LABEL: @test_mm512_reduce_min_epi64( -// CHECK: call i64 @llvm.vector.reduce.smin.v8i64(<8 x i64> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_min_epi64 +// CHECK: call {{.*}}i64 @llvm.vector.reduce.smin.v8i64(<8 x i64> %{{.*}}) return _mm512_reduce_min_epi64(__W); } +TEST_CONSTEXPR(_mm512_reduce_min_epi64((__m512i)(__v8di){-4, -3, -2, -1, 0, 1, 2, 3}) == -4); unsigned long long test_mm512_reduce_min_epu64(__m512i __W){ -// CHECK-LABEL: @test_mm512_reduce_min_epu64( -// CHECK: call i64 @llvm.vector.reduce.umin.v8i64(<8 x i64> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_min_epu64 +// CHECK: call {{.*}}i64 @llvm.vector.reduce.umin.v8i64(<8 x i64> %{{.*}}) return _mm512_reduce_min_epu64(__W); } +TEST_CONSTEXPR(_mm512_reduce_min_epu64((__m512i)(__v8du){0, 1, 2, 3, 4, 5, 6, 7}) == 0); double test_mm512_reduce_min_pd(__m512d __W, double ExtraMulOp){ -// CHECK-LABEL: @test_mm512_reduce_min_pd( +// CHECK-LABEL: test_mm512_reduce_min_pd // CHECK-NOT: nnan -// CHECK: call nnan double @llvm.vector.reduce.fmin.v8f64(<8 x double> %{{.*}}) +// CHECK: call nnan {{.*}}double @llvm.vector.reduce.fmin.v8f64(<8 x double> %{{.*}}) // CHECK-NOT: nnan return _mm512_reduce_min_pd(__W) * ExtraMulOp; } long long test_mm512_mask_reduce_max_epi64(__mmask8 __M, __m512i __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_max_epi64( +// CHECK-LABEL: test_mm512_mask_reduce_max_epi64 // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}} -// CHECK: call i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> %{{.*}}) +// CHECK: call {{.*}}i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> %{{.*}}) return _mm512_mask_reduce_max_epi64(__M, __W); } unsigned long test_mm512_mask_reduce_max_epu64(__mmask8 __M, __m512i __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_max_epu64( +// CHECK-LABEL: test_mm512_mask_reduce_max_epu64 // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}} -// CHECK: call i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> %{{.*}}) +// CHECK: call {{.*}}i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> %{{.*}}) return _mm512_mask_reduce_max_epu64(__M, __W); } double test_mm512_mask_reduce_max_pd(__mmask8 __M, __m512d __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_max_pd( +// CHECK-LABEL: test_mm512_mask_reduce_max_pd // CHECK: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}} -// CHECK: call nnan double @llvm.vector.reduce.fmax.v8f64(<8 x double> %{{.*}}) +// CHECK: call nnan {{.*}}double @llvm.vector.reduce.fmax.v8f64(<8 x double> %{{.*}}) return _mm512_mask_reduce_max_pd(__M, __W); } long long test_mm512_mask_reduce_min_epi64(__mmask8 __M, __m512i __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_min_epi64( +// CHECK-LABEL: test_mm512_mask_reduce_min_epi64 // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}} -// CHECK: call i64 @llvm.vector.reduce.smin.v8i64(<8 x i64> %{{.*}}) +// CHECK: call {{.*}}i64 @llvm.vector.reduce.smin.v8i64(<8 x i64> %{{.*}}) return _mm512_mask_reduce_min_epi64(__M, __W); } unsigned long long test_mm512_mask_reduce_min_epu64(__mmask8 __M, __m512i __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_min_epu64( +// CHECK-LABEL: test_mm512_mask_reduce_min_epu64 // CHECK: select <8 x i1> %{{.*}}, <8 x i64> %{{.*}}, <8 x i64> %{{.*}} -// CHECK: call i64 @llvm.vector.reduce.umin.v8i64(<8 x i64> %{{.*}}) +// CHECK: call {{.*}}i64 @llvm.vector.reduce.umin.v8i64(<8 x i64> %{{.*}}) return _mm512_mask_reduce_min_epu64(__M, __W); } double test_mm512_mask_reduce_min_pd(__mmask8 __M, __m512d __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_min_pd( +// CHECK-LABEL: test_mm512_mask_reduce_min_pd // CHECK: select <8 x i1> %{{.*}}, <8 x double> %{{.*}}, <8 x double> %{{.*}} -// CHECK: call nnan double @llvm.vector.reduce.fmin.v8f64(<8 x double> %{{.*}}) +// CHECK: call nnan {{.*}}double @llvm.vector.reduce.fmin.v8f64(<8 x double> %{{.*}}) return _mm512_mask_reduce_min_pd(__M, __W); } int test_mm512_reduce_max_epi32(__m512i __W){ -// CHECK-LABEL: @test_mm512_reduce_max_epi32( -// CHECK: call i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_max_epi32 +// CHECK: call {{.*}}i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> %{{.*}}) return _mm512_reduce_max_epi32(__W); } +TEST_CONSTEXPR(_mm512_reduce_max_epi32((__m512i)(__v16si){-8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7}) == 7); unsigned int test_mm512_reduce_max_epu32(__m512i __W){ -// CHECK-LABEL: @test_mm512_reduce_max_epu32( -// CHECK: call i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_max_epu32 +// CHECK: call {{.*}}i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> %{{.*}}) return _mm512_reduce_max_epu32(__W); } +TEST_CONSTEXPR(_mm512_reduce_max_epu32((__m512i)(__v16su){0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15}) == 15); float test_mm512_reduce_max_ps(__m512 __W){ -// CHECK-LABEL: @test_mm512_reduce_max_ps( -// CHECK: call nnan float @llvm.vector.reduce.fmax.v16f32(<16 x float> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_max_ps +// CHECK: call nnan {{.*}}float @llvm.vector.reduce.fmax.v16f32(<16 x float> %{{.*}}) return _mm512_reduce_max_ps(__W); } int test_mm512_reduce_min_epi32(__m512i __W){ -// CHECK-LABEL: @test_mm512_reduce_min_epi32( -// CHECK: call i32 @llvm.vector.reduce.smin.v16i32(<16 x i32> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_min_epi32 +// CHECK: call {{.*}}i32 @llvm.vector.reduce.smin.v16i32(<16 x i32> %{{.*}}) return _mm512_reduce_min_epi32(__W); } +TEST_CONSTEXPR(_mm512_reduce_min_epi32((__m512i)(__v16si){-8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7}) == -8); unsigned int test_mm512_reduce_min_epu32(__m512i __W){ -// CHECK-LABEL: @test_mm512_reduce_min_epu32( -// CHECK: call i32 @llvm.vector.reduce.umin.v16i32(<16 x i32> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_min_epu32 +// CHECK: call {{.*}}i32 @llvm.vector.reduce.umin.v16i32(<16 x i32> %{{.*}}) return _mm512_reduce_min_epu32(__W); } +TEST_CONSTEXPR(_mm512_reduce_min_epu32((__m512i)(__v16su){0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15}) == 0); float test_mm512_reduce_min_ps(__m512 __W){ -// CHECK-LABEL: @test_mm512_reduce_min_ps( -// CHECK: call nnan float @llvm.vector.reduce.fmin.v16f32(<16 x float> %{{.*}}) +// CHECK-LABEL: test_mm512_reduce_min_ps +// CHECK: call nnan {{.*}}float @llvm.vector.reduce.fmin.v16f32(<16 x float> %{{.*}}) return _mm512_reduce_min_ps(__W); } int test_mm512_mask_reduce_max_epi32(__mmask16 __M, __m512i __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_max_epi32( +// CHECK-LABEL: test_mm512_mask_reduce_max_epi32 // CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}} -// CHECK: call i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> %{{.*}}) +// CHECK: call {{.*}}i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> %{{.*}}) return _mm512_mask_reduce_max_epi32(__M, __W); } unsigned int test_mm512_mask_reduce_max_epu32(__mmask16 __M, __m512i __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_max_epu32( +// CHECK-LABEL: test_mm512_mask_reduce_max_epu32 // CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}} -// CHECK: call i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> %{{.*}}) +// CHECK: call {{.*}}i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> %{{.*}}) return _mm512_mask_reduce_max_epu32(__M, __W); } float test_mm512_mask_reduce_max_ps(__mmask16 __M, __m512 __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_max_ps( +// CHECK-LABEL: test_mm512_mask_reduce_max_ps // CHECK: select <16 x i1> %{{.*}}, <16 x float> %{{.*}}, <16 x float> %{{.*}} -// CHECK: call nnan float @llvm.vector.reduce.fmax.v16f32(<16 x float> %{{.*}}) +// CHECK: call nnan {{.*}}float @llvm.vector.reduce.fmax.v16f32(<16 x float> %{{.*}}) return _mm512_mask_reduce_max_ps(__M, __W); } int test_mm512_mask_reduce_min_epi32(__mmask16 __M, __m512i __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_min_epi32( +// CHECK-LABEL: test_mm512_mask_reduce_min_epi32 // CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}} -// CHECK: call i32 @llvm.vector.reduce.smin.v16i32(<16 x i32> %{{.*}}) +// CHECK: call {{.*}}i32 @llvm.vector.reduce.smin.v16i32(<16 x i32> %{{.*}}) return _mm512_mask_reduce_min_epi32(__M, __W); } unsigned int test_mm512_mask_reduce_min_epu32(__mmask16 __M, __m512i __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_min_epu32( +// CHECK-LABEL: test_mm512_mask_reduce_min_epu32 // CHECK: select <16 x i1> %{{.*}}, <16 x i32> %{{.*}}, <16 x i32> %{{.*}} -// CHECK: call i32 @llvm.vector.reduce.umin.v16i32(<16 x i32> %{{.*}}) +// CHECK: call {{.*}}i32 @llvm.vector.reduce.umin.v16i32(<16 x i32> %{{.*}}) return _mm512_mask_reduce_min_epu32(__M, __W); } float test_mm512_mask_reduce_min_ps(__mmask16 __M, __m512 __W){ -// CHECK-LABEL: @test_mm512_mask_reduce_min_ps( +// CHECK-LABEL: test_mm512_mask_reduce_min_ps // CHECK: select <16 x i1> %{{.*}}, <16 x float> %{{.*}}, <16 x float> %{{.*}} -// CHECK: call nnan float @llvm.vector.reduce.fmin.v16f32(<16 x float> %{{.*}}) +// CHECK: call nnan {{.*}}float @llvm.vector.reduce.fmin.v16f32(<16 x float> %{{.*}}) return _mm512_mask_reduce_min_ps(__M, __W); } - |